parsBERT_text_emotion_classification-finetuned-bmd-20241027_104504-LOSO-section-out5
This model is a fine-tuned version of Nhoseinnia/parsBERT_text_emotion_classification on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4624
- Accuracy: 0.3793
- F1: 0.3760
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 1.1314 | 1.0 | 4 | 1.1215 | 0.3448 | 0.1768 |
| 1.099 | 2.0 | 8 | 1.1121 | 0.3793 | 0.3634 |
| 0.9358 | 3.0 | 12 | 1.2410 | 0.4138 | 0.4128 |
| 0.8926 | 4.0 | 16 | 1.1374 | 0.3448 | 0.3531 |
| 0.7266 | 5.0 | 20 | 1.2135 | 0.3448 | 0.3448 |
| 0.5596 | 6.0 | 24 | 1.1618 | 0.3793 | 0.3810 |
| 0.4457 | 7.0 | 28 | 1.2940 | 0.3793 | 0.3810 |
| 0.3773 | 8.0 | 32 | 1.3599 | 0.3793 | 0.3868 |
| 0.2338 | 9.0 | 36 | 1.4399 | 0.3793 | 0.3760 |
| 0.2213 | 10.0 | 40 | 1.4624 | 0.3793 | 0.3760 |
Framework versions
- Transformers 4.46.0
- Pytorch 2.5.0+cu121
- Datasets 3.0.2
- Tokenizers 0.20.1